DA

cipher nano

DanubeGGUF by srock44Updated 2026-08-09
Download on Hugging Face
Parameters514M
Context8K
Layers16
Architecturellama
Smallest quant0.3 GB
Quick answer

cipher nano needs about 1.2 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

cipher nano is a 514M-parameter Danube model in GGUF format, quantized by srock44. Its trained context length is 8K tokens. The repository has 1 quant file, from 0.3 GB (Q4_K_M) to 0.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 1.2 GB
Fits Get file →

What GPU do you need for cipher nano?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q4_K_M (0.3 GB file, about 1.2 GB in use).

Which cipher nano quant should you choose?

Q4_K_M is the usual starting point for cipher nano: it balances file size and quality well. Here it is a 0.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters514M
Layers16
Trained context8,192 tokens
KV cache (fp16)48 KB per token

Source

Quantized bysrock44
FamilyDanube
Licenseapache-2.0
Downloads (HF)41
Last updated2026-08-09

Frequently asked questions about cipher nano

How much VRAM does cipher nano need?

About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run cipher nano on an 8 GB GPU?

Yes, with Q4_K_M: the 0.3 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cipher nano GGUF?

It depends on the quant: Q4_K_M is 0.3 GB.

What context length does cipher nano support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.

Where can I download cipher nano GGUF?

The files are on Hugging Face in the srock44/cipher-nano repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does cipher nano use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of h2o-danube3-500m-chat

Similar models

Browse all →

More from srock44

All by srock44 →

More Danube models

All Danube →

Other tiny models

All tiny models →